Annotating Multiple Sentences with Gene Entities Using PubTator

Question

[dolphin-sea]

Hi,

I need to annotate approximately 2,000 sentences for gene entities and their corresponding IDs (e.g., NCBI IDs) using PubTator. Based on their documentation, it seems I should use the API available at https://www.ncbi.nlm.nih.gov/CBBresearch/Lu/Demo/RESTful/request.cgi.

However, I’m unclear about how to send multiple sentences in a single request. Additionally, I need to ensure that the IDs I assign to each sentence are preserved in the response so I can keep track of them.

What would be the best way to handle this? Any guidance would be greatly appreciated.

Thanks!

[GenoMax]

approximately 2,000 sentences for gene entities and their corresponding IDs

What do you mean by "sentences"? Are you referring to 2000 rows of IDs? I don't see any way to send sentences in the API documentation that you linked above.

[dolphin-sea]

For the documentation, you can find the API usage for Named Entity Recognition under the title ‘Process Raw Text’ on that webpage. Regarding the sentences, that’s correct: I have a JSON file containing 2,000 individual sentences that I need to process using Pubtator to identify genes and their NCBI IDs. Additionally, I need to retain the sentence IDs from the JSON file.